Integrated and managed
Automate routine decisions, and steer them as you go.
Anthus can build Cyclotron into the tools your team already uses, then operate and improve it with you. Start with one recurring decision, set the evidence and review criteria together, and choose the level of help that fits: self-managed, Managed, or an ongoing integrated relationship.
This opens the existing enquiry form. Tell us the decision and tool involved; we can discuss the appropriate path without changing the form or promising a scheduling slot.
Three ways to decide at scale
Where your team's time goes.
People decide everything
Every decision is checked by someone who knows the business, and a team can only get through so many.
Off-the-shelf AI decides
It handles the volume, but nobody has checked it against your team's decisions, and its confidence does not tell you which decisions to look at.
Cyclotron
Your team steers with corrections and Cyclotron handles the volume. People check low-confidence decisions and a sample, so their time goes where it counts, and a monitor tracks results.
Since 2023, in production
Production experience that informs the work.
For Call Criteria, a quality assurance company for call centers, we built a classifier lab in the client's own AWS account. Hundreds of concurrent scorecards. Millions of calls scored in production. In many instances, a new scorecard was set up with AI assistance within an hour before a critical meeting or high-pressure moment. That is initial scorecard setup. Validation and production rollout have their own evaluation and review steps. The historical labels were unreliable, so the lab learned from live corrections instead. The client owns the models, the data, and the records.
This is operating history, not a promise that another team will get the same result. A new workflow needs its own evaluation and review criteria.
Illustrative product workflow
One rating control. A newsroom pattern.
Papyrus is Anthus's product-development newsroom. Reporter agents research before they write. The control below illustrates an editor rating a reference and explaining why, so that a cyclotron can evaluate later changes against that feedback.
Is this relevant to the publication?
Decision: include · 83% sure · version 3
Why you are seeing this: Sampled for audit at the 25% review rate.
Papyrus is a product-development example, not customer production evidence. The related simulated-feedback replay compares the raw decision model with Cyclotron's final prediction on the same final 140 recorded requests: accuracy 91.4% to 92.9% (rejecting everything would score 81.4%), recall 84.6% to 65.4%, and precision 73.3% to 94.4%. It is sequential with no independent holdout, and it does not establish production savings. Labels are simulated: two independent blind passes under a written policy; stories where the passes disagreed were left out.
Touch-points
The control your people already use.
- The approve and reject buttons in an editorial queue.
- The accept and discard buttons in a research or curation tool.
- The escalate control in a support desk.
- The audit form a QA reviewer already fills in.
What you are hiring
Evidence for the decision, and people to keep it current.
The work is choosing the decision, shaping the question, selecting the model, measuring errors, and deciding where people stay involved. We publish the evidence that informs those choices.
This is not legal advice. The benchmark pages connect what the models did in our tests to the rules that govern screening decisions. Whether a real use creates liability depends on the facts, the jurisdiction, and your lawyers.
The engagement
Start with one decision. Continue only if the relationship fits.
1
Discuss one workflow.Use the enquiry form to describe one recurring decision and the control your people already use. We discuss whether self-managed use, Managed support, or an integrated relationship fits that work.2
Agree the pilot.A fixed-price pilot is scoped with you. Its timing, baseline, representative evaluation, error tolerances, review effort, and cost are agreed for that workflow. We integrate one cyclotron at the touch-point, and your people can correct it during the pilot.3
Put one decision to work.The agreed pilot ends with one cyclotron live. Reviewers stay involved while you decide which cases can run automatically and which still need human review.4
Continue by choice.If you choose ongoing Integrated and managed, a named customer-success relationship meets with you weekly in the first eight weeks, then every two weeks. Monthly alignment reports and quarterly strategy reviews guide the next changes. Self-managed teams can keep operating Cyclotron without that relationship.
What an ongoing relationship includes
From $2,500 a month.
- Everything in Managed: the check-ins, the Slack channel, white-glove changes, and the monthly alignment review for each cyclotron.
- We integrate and maintain the code at the touch-point in your product.
- A named customer-success relationship and a quarterly strategy review.
- A dedicated AWS account you own, or one we run for you at cost.
- Bring your own key. Model usage is billed to you by your providers, never through us; we help you choose the provider and the model with the cost in front of you.
Pilot pricing is separately quoted after you discuss your workflow. More than 5 cyclotrons, or unusual infrastructure, is quoted as custom work.
Why monitoring continues
Drift happens, so cyclotrons stay under review.
Over time the items that arrive can change, and a cyclotron that was ready can get worse. Sampled reviews show it as falling accuracy. Each output is watched on its own, and the worst one sets the review rate. When a window of decisions ends below the target, the review rate goes up and your team checks more, until the cyclotron is aligned again.
Illustrative example. Monitoring continues after your team steps back.
Pilot criteria and limits
Agree the review plan before automation expands.
The pilot measures one cyclotron against your own representative corrections. It does not guarantee a particular accuracy or replace reviewers at the start. Together we decide the error tolerances, review effort, and evidence required before any wider automation. Where the line sits is part of the plan.
Start in the middle
People check what falls below the line, and a sample above it. Some mistakes still slip through.
Illustrative example. Positions show direction, not measured results. It assumes confidence already matches results.
This page does not set intellectual-property, access, or exit terms. Those are unresolved business terms to discuss before an engagement begins.
Discuss one recurring decision.
Tell us where your people already say yes or no. We can discuss whether Cyclotron fits there and whether you want to run it yourself or work with Anthus.
This opens the existing enquiry form; it is not a scheduler.